Elsalab
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Owners
        • Signed-in users
        • Everyone
        Owners Signed-in users Everyone
      • Write
        • Owners
        • Signed-in users
        • Everyone
        Owners Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights New
    • Engagement control
    • Make a copy
    • Transfer ownership
    • Delete this note
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Help
Menu
Options
Engagement control Make a copy Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Owners
  • Owners
  • Signed-in users
  • Everyone
Owners Signed-in users Everyone
Write
Owners
  • Owners
  • Signed-in users
  • Everyone
Owners Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    # Paper - CVPR (Unity-RL) ## Introduction * Optical flow as a mid-level representation for ***sim-to-real transfer*** on reinforcement learning * physical property? (a good good generalization property? proved by the speed experiments) * Previous methods mostly focus on semantic segmentation, depth maps, surface normals, or edges. * These mid-level represenations only capture static feature instead of motion features * good transfer property as we can simulate the object motion * We are the first paper investigating on the optical flow factorization? * Optical flow can be factorized into two different components * obj + ego >>>>>> all * this means we need * can we obtain the ego motion of the robot by camera calibration? if so, this means that we find a new way to improve the representation of optical flow. (practical deployment) * 可以實際 deploy 上機器人????? * Generalization capability of the motion? * We ablatively investigate on the representation of temporal information * Optical flow or stack frame? * Synergism of optical flow with the other mid-level representations ## Experiment Spec * https://hackmd.io/@Hsiao/r1zW622Zt * ## Background ### Optical flow estimation ### Mid-level representations ### (Optional) Sim-to-real transfer ## Factorization of Optical Flow * Simulator ? * Depth / Camera Intrisic / Extrinsic -> Ego motion ## Experiment Results ### Experimental Setups * Optical flow * Segmentation * Depth * Simulation environments * Evaluation metrics ### Flow Exps ![](https://i.imgur.com/Xg2p5Rw.png) * 補 Object Flow * 補 seed * 跑新的環境 - 從最好到最壞分別為 ego+obj、all、ego - ego+obj 優於 all 應該是因為 agent 能直接得知自己移動造成的 flow(ego)和人相對於自己的 flow(obj),而不需要從 all 中學到將兩者分離 - all 仍表現得不錯,或許是 agent 能學出類似 all == ego + obj 這樣的分解;另外也有可能真正重要的是不考慮 agent 自身位移,單純看物體本身的移動 - 單只有 ego 是表現最差的,推測可能是由於缺少物體本身移動而造成的 flow 資訊 ### Depth Exps ![](https://i.imgur.com/Rfj3Gv7.png) 由實驗的結果可觀察到: - 當 depth stack 數為 1 時,RL agent 是完全練不起來的。而隨著 stack 數量增加,agent 的表現也逐漸成長,代表若只有當下環境深度的資訊對於 agent 的學習並沒有幫助,還是需要仰賴物體移動的資訊才能讓 agent 對於環境的狀況更加了解 - single channel (grayscale) 的深度圖比起 multi channel 的深度圖對於 agent 更有幫助 - 使用 stack 超過一張的深度圖訓練時,代表 agent 可以獲得一些物體移動的資訊,但結果並不像使用 optical flow 訓練來得有效率,因為 agent 只能藉由 frame 與 frame 之間的關係來推斷物體的移動資訊,而 flow 是直接給予了 agent 環境中各物體的 motion 值,由此可知越清楚的 motion 資訊對於 agent 越有幫助,因此證明了 flow 是對於 agent 較有幫助的 representation ### Segmentation ![](https://i.imgur.com/wEvQckg.png =500x) * 單純bin_seg會練不起來,原因是agent會不知道路的邊界在哪,因此segmentation的邊界分割還是有其重要性在 * 加入raw image之後就可以train起來,但效果不如單純用segmentation,可見要再結合raw image對agent來說還是比較麻煩的 ### Observation with black background observation 除了人之外皆為黑色,包含object flow, instance flow, binary segmentation ![](https://i.imgur.com/7FnUeS8.png =500x) - 當只有stack 1 時,agent 皆練不起來,發現agent 失敗原因為經常走到道路外,代表如果agent 在observation 無法得到道路的資訊,沒辦法主動學到邊界訊息。 - 把raw image 也加入observation 後,reward 都可以超過0,其中instance flow 的表現最好。 - instance flow 表現較object flow 好,因為object flow 把自身移動消除,所以少了移動資訊後表現會更差。 - 將object flow stack 3 後表現超過binary segmentation stack 4(皆有加入raw image),表示把flow stack 多張後,agent 可以學到更多的資訊。 ### Generalization Capability * 比成功率: flow vs depth #### all_s1 v.s. ego_s1 + obj_s1 ![](https://i.imgur.com/ggOEGc3.png =360x) ### Temporal Information timestep (t, t+1) flow v.s. stacked (t, t+1) * Optical flow * Stacked segmentation? * Depth

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password

    or

    By clicking below, you agree to our terms of service.

    Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully